Top all-time · #3370
Sam Greydanus
Personal blog · greydanus.github.ioaiprogrammingscience
Sam Greydanus writes Natural Intelligence, a personal blog at greydanus.github.io about ai, programming and science. Since 2017, 22 different Hacker News readers have linked it 26 times, most often “Decoding the Enigma with Recurrent Neural Networks”. It is still writing: the last post was on 2026-07-20, and you can follow it by feed.
A blog by Sam Greydanus
Most-linked posts?
- Decoding the Enigma with Recurrent Neural Networks5 people · 5 mentions · first linked 2017-07-22
- Scaling Down Deep Learning5 people · 5 mentions · first linked 2020-12-02
- Hamiltonian Neural Networks3 people · 3 mentions · first linked 2019-06-17
- Finding paths of least action with gradient descent (2023)2 people · 2 mentions · first linked 2023-03-06
- Optimizing a Wing2 people · 2 mentions · first linked 2020-10-19
What Hacker News says?
I found the previous Hamiltonian Neural Networks [0]. If the authors are here, I'd be interested to use [1] for a version with dissipation. [0] https://greydanus.github.io/2019/05/15/hamiltonian-nns/ [1] https://arxiv.org/abs/1902.04598
Comment linking /2019/05/15/hamiltonian-nns/
on “Lagrangian Neural Networks”Submitted Lagrangian Neural Networks as a story · 246 points
HN discussionSome of the older posts are very cute. I enjoyed https://greydanus.github.io/2020/12/01/scaling-down/ on showing how many high-powered tricks you can do with a tiny NN of the sort that will train in seconds.
Comment linking /2020/12/01/scaling-down/
on “Finding paths of least action with gradient descent (2023)”Submitted Scaling Down Deep Learning as a story · 124 points
HN discussionThis is a beautiful blog, e.g. this one is one of my favorites https://greydanus.github.io/2020/10/14/optimizing-a-wing/
Comment linking /2020/10/14/optimizing-a-wing/
on “Scaling Down Deep Learning”Submitted Finding paths of least action with gradient descent (2023) as a story · 73 points
HN discussionI remember John Carlos Baez having some interesting stuff: https://johncarlosbaez.wordpress.com/ Some other ones I had bookmarked the other day but haven't seen much in depth, mostly computer science based but more towards theory/math side: https://blog.computationalcomplexity.org/ https://semantic-domain.blogspot.com/ https://greydanus.github.io/ Also go to Terry Tao's blog and look at the sidebar, there are a lot…
Comment linking /
on “Ask HN: What are some interesting math and physics blogs you follow?”Submitted Optimizing a Wing as a story · 13 points
HN discussionThis is somewhat related: how do we build datasets that are better discriminators of model architectures, and are also easier to experiment on? https://greydanus.github.io/2020/12/01/scaling-down/
Comment linking /2020/12/01/scaling-down/
on “A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet”Submitted Scaling Down Deep Learning as a story · 8 points
HN discussionOriginal source, https://greydanus.github.io/2017/01/07/enigma-rnn/
Comment linking /2017/01/07/enigma-rnn/
on “Decoding Enigma using a neural network”Submitted Decoding the Enigma with Recurrent Neural Networks as a story · 4 points
HN discussionSubmitted Decoding the Enigma with Recurrent Neural Networks as a story · 4 points
HN discussionSubmitted Neural Reparameterization Improves Structural Optimization as a story · 3 points
HN discussionSubmitted Simulating the Universe Could Yield Quantum Mechanics as a story · 3 points
HN discussionSubmitted Three Perspectives on Deep Learning as a story · 3 points
HN discussionSubmitted A Structural Optimization Tutorial as a story · 2 points
HN discussionSubmitted Scaling Down Deep Learning as a story · 2 points
HN discussionSubmitted Hamiltonian Neural Networks as a story · 2 points
HN discussionSubmitted Learning the Enigma with RNNs as a story · 2 points
HN discussionSubmitted Moviescape: Google Maps for Cinema as a story · 1 points
HN discussionSubmitted The Cursive Transformer as a story · 1 points
HN discussionSubmitted Finding Paths of Least Action with Gradient Descent as a story · 1 points
HN discussionSubmitted Hamiltonian Neural Networks as a story · 1 points
HN discussionSubmitted Decoding the Enigma with Recurrent Neural Networks as a story · 1 points
HN discussionSubmitted Decoding the Enigma with Recurrent Neural Networks as a story · 1 points
HN discussion
